© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 54386
    Prev
    Next
    INDEX
    Explanations

    about, for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     اÙĦÙĤاد
    -0.09
     знак
    -0.08
    åĮĸçļĦ
    -0.08
    æĸ°å¨ĺ
    -0.08
    ably
    -0.08
    æ½į
    -0.08
    tsy
    -0.08
    ÃĤN
    -0.08
    æīĭä¸ŃçļĦ
    -0.08
    anded
    -0.08
    POSITIVE LOGITS
    楫
    0.10
     ÙĪÙħا
    0.10
    ä¿ij
    0.10
    æĬĹéľĩ
    0.09
    管å±Ģ
    0.09
    çŁį
    0.08
    ä¸ľè¥¿
    0.08
    lops
    0.08
    za
    0.08
    -shell
    0.08
    Activations Density 0.033%

    No Known Activations